AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 247
On the Calibration of Crowdsourcing Aggregators
Calibration has been extensively studied for classifiers, but remains largely unexplored for crowdsourcing aggregation methods, which are increasingly used for making probabilistic decisions.Statistical Downscaling of Daily Precipitation from ERA5 Atmospheric Fields to IMERG over West Africa
Global reanalyses are too coarse to resolve the convective systems that produce most West African monsoon rainfall.Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers
Progressive depth growth builds large networks by starting with shallow models and inserting layers during training.Calibrated $α$-Barycenters for Multiobjective $f$-Divergence Optimization
Matching one distribution to many targets can require repeated evaluations of every target.Sample-Size Extrapolation in Simulation-Based Inference via Statistical Scaling
In simulation-based inference (SBI), neural posterior estimators trained on a bounded range of sample sizes can become inaccurate on larger datasets because their parameterizations do not specify…DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning
Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates.Mean Accuracy Is the Wrong Estimand for a Release Decision
A release decision about a fine-tuned model is an operational commitment about the \emph{next} rerun of its training recipe.Unsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors
Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording conditions, with labels…The Bell Boundary of Shared Representations
When does a shared representation become insufficient for jointly supporting multiple tasks?Few-for-Many Best-Arm Identification in Multi-Objective Bandits
Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback.Feature Normalization under Finite Training Budgets
Standardizing a rare feature can help stochastic gradient descent learn its effect within a finite budget, but it also changes the noise cost of learning.Radial Tail Repair: Post-Training Correction for Diffusion and Flow Models
Diffusion and flow-matching models may struggle to accurately represent distributional tails, especially for heavy-tailed data.GpFlash: Maximizing Speed and Minimizing Memory for Gaussian Process Training and Prediction
This paper presents GpFlash, a Gaussian process library that is focused on fast training and posterior evaluations, minimal memory usage, and scalability to high-dimensional problems.Better together? A performance theory of human-machine skill policies under generalization difficulty
Organizations pairing a human and a machine on a task decide, often by default, which executes each instance and what happens when both do.Efficient Resource-Shiftable RL Post-training with Generative Rewards
Reinforcement learning (RL) post-training with generative reward models (GenRM) has become a central recipe for improving large language models (LLMs), and it is also increasingly…Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments
Reliable agentic tool use requires training data that pair diverse multi-step workflows with executable evidence that the requested outcomes were achieved.From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon
Simplicity bias, which can arise from sequential feature learning during training, has been proposed as a general explanation for the success of deep learning.Sequence Composition in EHR Foundation Model Pretraining
Autoregressive electronic health record (EHR) foundation models predict the next event token in patient trajectories: sequences of structured medical events.Learning Operators for Symmetry Discovery: From Lie Groups to Local Symmetry Geometry
Continuous symmetry discovery is typically formulated as a separate estimation problem for each function or dataset.FORGE: Procedural Weight Generation for Sparse MoE Inference
We introduce FORGE (Fast On-chip Rotor Generation for Experts), a procedural weight generation system for Sparse Mixture-of-Experts (MoE) inference.